enum sgp_type {
SGP_READ, /* don't exceed i_size, don't allocate page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
+ SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */
SGP_WRITE, /* may exceed i_size, may allocate page */
};
};
static LIST_HEAD(shmem_swaplist);
-static DEFINE_SPINLOCK(shmem_swaplist_lock);
+static DEFINE_MUTEX(shmem_swaplist_mutex);
static void shmem_free_blocks(struct inode *inode, long pages)
{
inode->i_size = 0;
shmem_truncate(inode);
if (!list_empty(&info->swaplist)) {
- spin_lock(&shmem_swaplist_lock);
+ mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
- spin_unlock(&shmem_swaplist_lock);
+ mutex_unlock(&shmem_swaplist_mutex);
}
}
BUG_ON(inode->i_blocks);
struct page *subdir;
swp_entry_t *ptr;
int offset;
+ int error;
idx = 0;
ptr = info->i_direct;
spin_lock(&info->lock);
+ if (!info->swapped) {
+ list_del_init(&info->swaplist);
+ goto lost2;
+ }
limit = info->next_index;
size = limit;
if (size > SHMEM_NR_DIRECT)
size = SHMEM_NR_DIRECT;
offset = shmem_find_swp(entry, ptr, ptr+size);
- if (offset >= 0) {
- shmem_swp_balance_unmap();
+ if (offset >= 0)
goto found;
- }
if (!info->i_indirect)
goto lost2;
for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) {
if (unlikely(idx == stage)) {
shmem_dir_unmap(dir-1);
+ if (cond_resched_lock(&info->lock)) {
+ /* check it has not been truncated */
+ if (limit > info->next_index) {
+ limit = info->next_index;
+ if (idx >= limit)
+ goto lost2;
+ }
+ }
dir = shmem_dir_map(info->i_indirect) +
ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
while (!*dir) {
if (size > ENTRIES_PER_PAGE)
size = ENTRIES_PER_PAGE;
offset = shmem_find_swp(entry, ptr, ptr+size);
+ shmem_swp_unmap(ptr);
if (offset >= 0) {
shmem_dir_unmap(dir);
goto found;
}
- shmem_swp_unmap(ptr);
}
}
lost1:
return 0;
found:
idx += offset;
- inode = &info->vfs_inode;
- if (add_to_page_cache(page, inode->i_mapping, idx, GFP_ATOMIC) == 0) {
+ inode = igrab(&info->vfs_inode);
+ spin_unlock(&info->lock);
+
+ /*
+ * Move _head_ to start search for next from here.
+ * But be careful: shmem_delete_inode checks list_empty without taking
+ * mutex, and there's an instant in list_move_tail when info->swaplist
+ * would appear empty, if it were the only one on shmem_swaplist. We
+ * could avoid doing it if inode NULL; or use this minor optimization.
+ */
+ if (shmem_swaplist.next != &info->swaplist)
+ list_move_tail(&shmem_swaplist, &info->swaplist);
+ mutex_unlock(&shmem_swaplist_mutex);
+
+ error = 1;
+ if (!inode)
+ goto out;
+ error = radix_tree_preload(GFP_KERNEL);
+ if (error)
+ goto out;
+ error = 1;
+
+ spin_lock(&info->lock);
+ ptr = shmem_swp_entry(info, idx, NULL);
+ if (ptr && ptr->val == entry.val)
+ error = add_to_page_cache(page, inode->i_mapping,
+ idx, GFP_NOWAIT);
+ if (error == -EEXIST) {
+ struct page *filepage = find_get_page(inode->i_mapping, idx);
+ error = 1;
+ if (filepage) {
+ /*
+ * There might be a more uptodate page coming down
+ * from a stacked writepage: forget our swappage if so.
+ */
+ if (PageUptodate(filepage))
+ error = 0;
+ page_cache_release(filepage);
+ }
+ }
+ if (!error) {
delete_from_swap_cache(page);
set_page_dirty(page);
info->flags |= SHMEM_PAGEIN;
- shmem_swp_set(info, ptr + offset, 0);
+ shmem_swp_set(info, ptr, 0);
+ swap_free(entry);
+ error = 1; /* not an error, but entry was found */
}
- shmem_swp_unmap(ptr);
+ if (ptr)
+ shmem_swp_unmap(ptr);
spin_unlock(&info->lock);
- /*
- * Decrement swap count even when the entry is left behind:
- * try_to_unuse will skip over mms, then reincrement count.
- */
- swap_free(entry);
- return 1;
+ radix_tree_preload_end();
+out:
+ unlock_page(page);
+ page_cache_release(page);
+ iput(inode); /* allows for NULL */
+ return error;
}
/*
struct shmem_inode_info *info;
int found = 0;
- spin_lock(&shmem_swaplist_lock);
+ mutex_lock(&shmem_swaplist_mutex);
list_for_each_safe(p, next, &shmem_swaplist) {
info = list_entry(p, struct shmem_inode_info, swaplist);
- if (!info->swapped)
- list_del_init(&info->swaplist);
- else if (shmem_unuse_inode(info, entry, page)) {
- /* move head to start search for next from here */
- list_move_tail(&shmem_swaplist, &info->swaplist);
- found = 1;
- break;
- }
+ found = shmem_unuse_inode(info, entry, page);
+ cond_resched();
+ if (found)
+ goto out;
}
- spin_unlock(&shmem_swaplist_lock);
- return found;
+ mutex_unlock(&shmem_swaplist_mutex);
+out: return found; /* 0 or 1 or -ENOMEM */
}
/*
struct inode *inode;
BUG_ON(!PageLocked(page));
- /*
- * shmem_backing_dev_info's capabilities prevent regular writeback or
- * sync from ever calling shmem_writepage; but a stacking filesystem
- * may use the ->writepage of its underlying filesystem, in which case
- * we want to do nothing when that underlying filesystem is tmpfs
- * (writing out to swap is useful as a response to memory pressure, but
- * of no use to stabilize the data) - just redirty the page, unlock it
- * and claim success in this case. AOP_WRITEPAGE_ACTIVATE, and the
- * page_mapped check below, must be avoided unless we're in reclaim.
- */
- if (!wbc->for_reclaim) {
- set_page_dirty(page);
- unlock_page(page);
- return 0;
- }
- BUG_ON(page_mapped(page));
-
mapping = page->mapping;
index = page->index;
inode = mapping->host;
info = SHMEM_I(inode);
if (info->flags & VM_LOCKED)
goto redirty;
- swap = get_swap_page();
- if (!swap.val)
+ if (!total_swap_pages)
goto redirty;
+ /*
+ * shmem_backing_dev_info's capabilities prevent regular writeback or
+ * sync from ever calling shmem_writepage; but a stacking filesystem
+ * may use the ->writepage of its underlying filesystem, in which case
+ * tmpfs should write out to swap only in response to memory pressure,
+ * and not for pdflush or sync. However, in those cases, we do still
+ * want to check if there's a redundant swappage to be discarded.
+ */
+ if (wbc->for_reclaim)
+ swap = get_swap_page();
+ else
+ swap.val = 0;
+
spin_lock(&info->lock);
- shmem_recalc_inode(inode);
if (index >= info->next_index) {
BUG_ON(!(info->flags & SHMEM_TRUNCATE));
goto unlock;
}
entry = shmem_swp_entry(info, index, NULL);
- BUG_ON(!entry);
- BUG_ON(entry->val);
+ if (entry->val) {
+ /*
+ * The more uptodate page coming down from a stacked
+ * writepage should replace our old swappage.
+ */
+ free_swap_and_cache(*entry);
+ shmem_swp_set(info, entry, 0);
+ }
+ shmem_recalc_inode(inode);
- if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
+ if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
remove_from_page_cache(page);
shmem_swp_set(info, entry, swap.val);
shmem_swp_unmap(entry);
+ if (list_empty(&info->swaplist))
+ inode = igrab(inode);
+ else
+ inode = NULL;
spin_unlock(&info->lock);
- if (list_empty(&info->swaplist)) {
- spin_lock(&shmem_swaplist_lock);
- /* move instead of add in case we're racing */
- list_move_tail(&info->swaplist, &shmem_swaplist);
- spin_unlock(&shmem_swaplist_lock);
- }
swap_duplicate(swap);
+ BUG_ON(page_mapped(page));
page_cache_release(page); /* pagecache ref */
set_page_dirty(page);
unlock_page(page);
+ if (inode) {
+ mutex_lock(&shmem_swaplist_mutex);
+ /* move instead of add in case we're racing */
+ list_move_tail(&info->swaplist, &shmem_swaplist);
+ mutex_unlock(&shmem_swaplist_mutex);
+ iput(inode);
+ }
return 0;
}
swap_free(swap);
redirty:
set_page_dirty(page);
- return AOP_WRITEPAGE_ACTIVATE; /* Return with the page locked */
+ if (wbc->for_reclaim)
+ return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */
+ unlock_page(page);
+ return 0;
}
#ifdef CONFIG_NUMA
goto done;
error = 0;
gfp = mapping_gfp_mask(mapping);
+ if (!filepage) {
+ /*
+ * Try to preload while we can wait, to not make a habit of
+ * draining atomic reserves; but don't latch on to this cpu.
+ */
+ error = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
+ if (error)
+ goto failed;
+ radix_tree_preload_end();
+ }
spin_lock(&info->lock);
shmem_recalc_inode(inode);
set_page_dirty(filepage);
swap_free(swap);
} else if (!(error = add_to_page_cache(
- swappage, mapping, idx, GFP_ATOMIC))) {
+ swappage, mapping, idx, GFP_NOWAIT))) {
info->flags |= SHMEM_PAGEIN;
shmem_swp_set(info, entry, 0);
shmem_swp_unmap(entry);
spin_unlock(&info->lock);
unlock_page(swappage);
page_cache_release(swappage);
- if (error == -ENOMEM) {
- /* let kswapd refresh zone for GFP_ATOMICs */
- congestion_wait(WRITE, HZ/50);
- }
goto repeat;
}
} else if (sgp == SGP_READ && !filepage) {
shmem_swp_unmap(entry);
}
if (error || swap.val || 0 != add_to_page_cache_lru(
- filepage, mapping, idx, GFP_ATOMIC)) {
+ filepage, mapping, idx, GFP_NOWAIT)) {
spin_unlock(&info->lock);
page_cache_release(filepage);
shmem_unacct_blocks(info->flags, 1);
clear_highpage(filepage);
flush_dcache_page(filepage);
SetPageUptodate(filepage);
+ if (sgp == SGP_DIRTY)
+ set_page_dirty(filepage);
}
done:
*pagep = filepage;
struct inode *inode = filp->f_path.dentry->d_inode;
struct address_space *mapping = inode->i_mapping;
unsigned long index, offset;
+ enum sgp_type sgp = SGP_READ;
+
+ /*
+ * Might this read be for a stacking filesystem? Then when reading
+ * holes of a sparse file, we actually need to allocate those pages,
+ * and even mark them dirty, so it cannot exceed the max_blocks limit.
+ */
+ if (segment_eq(get_fs(), KERNEL_DS))
+ sgp = SGP_DIRTY;
index = *ppos >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
break;
}
- desc->error = shmem_getpage(inode, index, &page, SGP_READ, NULL);
+ desc->error = shmem_getpage(inode, index, &page, sgp, NULL);
if (desc->error) {
if (desc->error == -EINVAL)
desc->error = 0;
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return security_inode_getsecurity(inode, name, buffer, size,
- -EOPNOTSUPP);
+ return xattr_getsecurity(inode, name, buffer, size);
}
static int shmem_xattr_security_set(struct inode *inode, const char *name,